Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy

M. E. Rettmann, T. Stephens, David R. Holmes III, C. Linte, Douglas L Packer, R. A. Robb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Intracardiac echocardiography (ICE), a technique in which structures of the heart are imaged using a catheter navigated inside the cardiac chambers, is an important imaging technique for guidance in cardiac ablation therapy. Automatic segmentation of these images is valuable for guidance and targeting of treatment sites. In this paper, we describe an approach to segment ICE images by generating an empirical model of blood pool and tissue intensities. Normal, Weibull, Gamma, and Generalized Extreme Value (GEV) distributions are fit to histograms of tissue and blood pool pixels from a series of ICE scans. A total of 40 images from 4 separate studies were evaluated. The model was trained and tested using two approaches. In the first approach, the model was trained on all images from 3 studies and subsequently tested on the 40 images from the 4th study. This procedure was repeated 4 times using a leave-one-out strategy. This is termed the between-subjects approach. In the second approach, the model was trained on 10 randomly selected images from a single study and tested on the remaining 30 images in that study. This is termed the within-subjects approach. For both approaches, the model was used to automatically segment ICE images into blood and tissue regions. Each pixel is classified using the Generalized Liklihood Ratio Test across neighborhood sizes ranging from 1 to 49. Automatic segmentation results were compared against manual segmentations for all images. In the between-subjects approach, the GEV distribution using a neighborhood size of 17 was found to be the most accurate with a misclassification rate of approximately 17%. In the within-subjects approach, the GEV distribution using a neighborhood size of 19 was found to be the most accurate with a misclassification rate of approximately 15%. As expected, the majority of misclassified pixels were located near the boundaries between tissue and blood pool regions for both methods.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume8671
DOIs
StatePublished - 2013
EventMedical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling - Lake Buena Vista, FL, United States
Duration: Feb 12 2013Feb 14 2013

Other

OtherMedical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CityLake Buena Vista, FL
Period2/12/132/14/13

Fingerprint

Ultrasound Image
Ablation
Echocardiography
Cardiac
ablation
Therapy
therapy
Segmentation
Ultrasonics
Blood
echocardiography
Tissue
Generalized Extreme Value Distribution
Pixels
blood
Misclassification Rate
Pixel
pixels
Catheters
Guidance

Keywords

  • Image-guided interventions
  • Intra-cardiac ultrasound
  • Left atrium
  • Ultrasound segmentation

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Rettmann, M. E., Stephens, T., Holmes III, D. R., Linte, C., Packer, D. L., & Robb, R. A. (2013). Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 8671). [86712D] https://doi.org/10.1117/12.2008762

Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy. / Rettmann, M. E.; Stephens, T.; Holmes III, David R.; Linte, C.; Packer, Douglas L; Robb, R. A.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671 2013. 86712D.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rettmann, ME, Stephens, T, Holmes III, DR, Linte, C, Packer, DL & Robb, RA 2013, Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 8671, 86712D, Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling, Lake Buena Vista, FL, United States, 2/12/13. https://doi.org/10.1117/12.2008762
Rettmann ME, Stephens T, Holmes III DR, Linte C, Packer DL, Robb RA. Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671. 2013. 86712D https://doi.org/10.1117/12.2008762
Rettmann, M. E. ; Stephens, T. ; Holmes III, David R. ; Linte, C. ; Packer, Douglas L ; Robb, R. A. / Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8671 2013.
@inproceedings{0ce8d19e492748f99e739eb2f9b44956,
title = "Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy",
abstract = "Intracardiac echocardiography (ICE), a technique in which structures of the heart are imaged using a catheter navigated inside the cardiac chambers, is an important imaging technique for guidance in cardiac ablation therapy. Automatic segmentation of these images is valuable for guidance and targeting of treatment sites. In this paper, we describe an approach to segment ICE images by generating an empirical model of blood pool and tissue intensities. Normal, Weibull, Gamma, and Generalized Extreme Value (GEV) distributions are fit to histograms of tissue and blood pool pixels from a series of ICE scans. A total of 40 images from 4 separate studies were evaluated. The model was trained and tested using two approaches. In the first approach, the model was trained on all images from 3 studies and subsequently tested on the 40 images from the 4th study. This procedure was repeated 4 times using a leave-one-out strategy. This is termed the between-subjects approach. In the second approach, the model was trained on 10 randomly selected images from a single study and tested on the remaining 30 images in that study. This is termed the within-subjects approach. For both approaches, the model was used to automatically segment ICE images into blood and tissue regions. Each pixel is classified using the Generalized Liklihood Ratio Test across neighborhood sizes ranging from 1 to 49. Automatic segmentation results were compared against manual segmentations for all images. In the between-subjects approach, the GEV distribution using a neighborhood size of 17 was found to be the most accurate with a misclassification rate of approximately 17{\%}. In the within-subjects approach, the GEV distribution using a neighborhood size of 19 was found to be the most accurate with a misclassification rate of approximately 15{\%}. As expected, the majority of misclassified pixels were located near the boundaries between tissue and blood pool regions for both methods.",
keywords = "Image-guided interventions, Intra-cardiac ultrasound, Left atrium, Ultrasound segmentation",
author = "Rettmann, {M. E.} and T. Stephens and {Holmes III}, {David R.} and C. Linte and Packer, {Douglas L} and Robb, {R. A.}",
year = "2013",
doi = "10.1117/12.2008762",
language = "English (US)",
isbn = "9780819494450",
volume = "8671",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy

AU - Rettmann, M. E.

AU - Stephens, T.

AU - Holmes III, David R.

AU - Linte, C.

AU - Packer, Douglas L

AU - Robb, R. A.

PY - 2013

Y1 - 2013

N2 - Intracardiac echocardiography (ICE), a technique in which structures of the heart are imaged using a catheter navigated inside the cardiac chambers, is an important imaging technique for guidance in cardiac ablation therapy. Automatic segmentation of these images is valuable for guidance and targeting of treatment sites. In this paper, we describe an approach to segment ICE images by generating an empirical model of blood pool and tissue intensities. Normal, Weibull, Gamma, and Generalized Extreme Value (GEV) distributions are fit to histograms of tissue and blood pool pixels from a series of ICE scans. A total of 40 images from 4 separate studies were evaluated. The model was trained and tested using two approaches. In the first approach, the model was trained on all images from 3 studies and subsequently tested on the 40 images from the 4th study. This procedure was repeated 4 times using a leave-one-out strategy. This is termed the between-subjects approach. In the second approach, the model was trained on 10 randomly selected images from a single study and tested on the remaining 30 images in that study. This is termed the within-subjects approach. For both approaches, the model was used to automatically segment ICE images into blood and tissue regions. Each pixel is classified using the Generalized Liklihood Ratio Test across neighborhood sizes ranging from 1 to 49. Automatic segmentation results were compared against manual segmentations for all images. In the between-subjects approach, the GEV distribution using a neighborhood size of 17 was found to be the most accurate with a misclassification rate of approximately 17%. In the within-subjects approach, the GEV distribution using a neighborhood size of 19 was found to be the most accurate with a misclassification rate of approximately 15%. As expected, the majority of misclassified pixels were located near the boundaries between tissue and blood pool regions for both methods.

AB - Intracardiac echocardiography (ICE), a technique in which structures of the heart are imaged using a catheter navigated inside the cardiac chambers, is an important imaging technique for guidance in cardiac ablation therapy. Automatic segmentation of these images is valuable for guidance and targeting of treatment sites. In this paper, we describe an approach to segment ICE images by generating an empirical model of blood pool and tissue intensities. Normal, Weibull, Gamma, and Generalized Extreme Value (GEV) distributions are fit to histograms of tissue and blood pool pixels from a series of ICE scans. A total of 40 images from 4 separate studies were evaluated. The model was trained and tested using two approaches. In the first approach, the model was trained on all images from 3 studies and subsequently tested on the 40 images from the 4th study. This procedure was repeated 4 times using a leave-one-out strategy. This is termed the between-subjects approach. In the second approach, the model was trained on 10 randomly selected images from a single study and tested on the remaining 30 images in that study. This is termed the within-subjects approach. For both approaches, the model was used to automatically segment ICE images into blood and tissue regions. Each pixel is classified using the Generalized Liklihood Ratio Test across neighborhood sizes ranging from 1 to 49. Automatic segmentation results were compared against manual segmentations for all images. In the between-subjects approach, the GEV distribution using a neighborhood size of 17 was found to be the most accurate with a misclassification rate of approximately 17%. In the within-subjects approach, the GEV distribution using a neighborhood size of 19 was found to be the most accurate with a misclassification rate of approximately 15%. As expected, the majority of misclassified pixels were located near the boundaries between tissue and blood pool regions for both methods.

KW - Image-guided interventions

KW - Intra-cardiac ultrasound

KW - Left atrium

KW - Ultrasound segmentation

UR - http://www.scopus.com/inward/record.url?scp=84878589752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878589752&partnerID=8YFLogxK

U2 - 10.1117/12.2008762

DO - 10.1117/12.2008762

M3 - Conference contribution

AN - SCOPUS:84878589752

SN - 9780819494450

VL - 8671

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -